首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于边缘特征的运动目标提取与跟踪
引用本文:张桂林,张天序,魏洛刚,谢先明.基于边缘特征的运动目标提取与跟踪[J].华中科技大学学报(自然科学版),1994(5).
作者姓名:张桂林  张天序  魏洛刚  谢先明
作者单位:华中理工大学图像识别与人工智能研究所
摘    要:运用聚类准则,提出了一种获取二值边缘图的自动门限法,研究了序列图像中目标跟踪窗的自适应调整,并在此基础上进行了复杂背景中运动目标匹配跟踪试验。试验结果表明,本方法提高了复杂背景中运动目标跟踪的能力,可作为常规跟踪方法的补充,以达到稳定跟踪。

关 键 词:特征提取,二值模板匹配,目标跟踪,机器视觉,序列图像处理

An Edge-feature-based Approach to the Extraction and Tracking of a Moving Object
Zhang GuilinInst.of Pattern Recognition &AI,H.U.S.T.,Wuhan ,China.,Zhang Tianxu,Wei Luogang,Xei Luogang,Xie Xianming.An Edge-feature-based Approach to the Extraction and Tracking of a Moving Object[J].JOURNAL OF HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY.NATURE SCIENCE,1994(5).
Authors:Zhang GuilinInstof Pattern Recognition &AI  HUST  Wuhan  China  Zhang Tianxu  Wei Luogang  Xei Luogang  Xie Xianming
Institution:Zhang GuilinInst.of Pattern Recognition &AI,H.U.S.T.,Wuhan 430074,China.,Zhang Tianxu,Wei Luogang,Xei Luogang,Xie Xianming
Abstract:The edge features of an object image are relatively stable and can be raedily detected.An automated thresholding for generating a binary edge map is developed with the clusterctiterion;The adaptive adjustment of the tracking window in sequential images is discussed.Experimental results of moving object tracking by edge template matching in a complex back-ground are given,It is shown that the method proposed can improve the performance of theobject tracking system.
Keywords:feature extraction  binary template matching  object tracking  machine vision  sequential image processing  
本文献已被 CNKI 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号